Tuesday, October 27, 2026i10X News · Section desk7 stories
Studies
Reasoning
Reasoning, planning, math and chain-of-thought research
FilterMeta
Filtered: Meta in Reasoning · 1 storyReset filter ×
-
RL Post-Training Makes Agents More Accurate — and Less Able to Explore
Across 14 base/post-trained pairs on 3 agentic benches, base models often beat RL successors at pass@K. On WebShop, gemma-4-31B’s “pass given compute” shrinks from 87.6% to 30.0% after RL.
By
Editor's picks
- Randomly Evicting KV Cache Matches Smart Selectors — and Runs 32–43% Faster
- A 150M Model Hits 29.5% on ARC-AGI-1 for Under a Tenth of a Cent
- RL for Reasoning Wastes Gradient on Formatting Tokens. DelTA Fixes the Credit
- Distill the RL Direction in Hidden Space, Not Noisy Output Rewards
- A 3B Model Hits 94.3 on AIME26 and 80.2 on LiveCodeBench
More stories
· RSS